Quality Framework - UNSD

Quality Framework - UNSD

United Nations Economic Commission for Europe Statistical Division Imputation in UNECE Statistical Databases: Principles and Practices Steven Vale and Heinrich Brngger, UNECE Statistical Division Contents The ECOSOC view of statistical imputation Current practices Basic principles Step-by-step implementation Conclusions and open questions March 1, 2020

Steven Vale - UNECE Statistical Division Slide 2 ECOSOC views Resolution 2006/6 on strengthening statistical capacity Sets limits for the use of imputation ... but also implicitly endorses it as a statistical technique Statistical agencies need to review their practices to ensure compliance Steven Vale - UNECE Statistical Division

Slide 3 Defining imputation A procedure for entering a value for a specific data item where the response is missing or unusable Boundary issues: Imputing and editing Imputing and forecasting Steven Vale - UNECE Statistical Division Slide 4 Current practice in UNECE

Very limited ad-hoc imputation Four cases: Account identities Regional aggregates Poor quality national data with little impact on region totals Re-classification Using imputations from others

Sufficient transparency in source metadata? Steven Vale - UNECE Statistical Division Slide 5 Basic principles (1) Imputed national data are not published Avoids the need for consultation Only official sources used for imputation Preference for data from same country Clear distinction between real and

imputed data Transparency imputed data clearly flagged, and methods documented Steven Vale - UNECE Statistical Division Slide 6 Basic principles (2) Aggregates must contain > 90% real data, covering > 50% of countries Imputed data are re-calculated periodically to adjust for revisions Method used defined at the level of the variable and stored as an attribute

Decisions on the use of imputation to be taken with regard to the quality framework Steven Vale - UNECE Statistical Division Slide 7 Step-by-step application Automatic imputation routines to extend imputation towards the boundaries set by the ECOSOC Resolution One step at a time, with pause and review to consider quality and cost / benefit Dashboard to allow statisticians to choose the most appropriate method

Implemented in the context of reengineering of statistical database system Steven Vale - UNECE Statistical Division Slide 8 First step Use a linear trend to impute missing values Requirements: Sufficient time series observations (at least 3 out of previous 5 periods) Closeness of fit of linear trend (R2 close to 1) Constraints

Validity of R2 for few observations Forward imputation only Steven Vale - UNECE Statistical Division Slide 9 2000 2001 2002 2003 2004 2005 2006 2007 N Y Y N Y Y N

Data Available: Imputation: Y = Yes = Yes N = No = No Steven Vale - UNECE Statistical Division N Slide 10 Next steps More flexibility:

Longer time series Imputing values at start and in middle of time series Non-linear trends? Cross-country imputation in strictly limited cases? Steven Vale - UNECE Statistical Division Slide 11 Conclusions Strong links between imputation and quality

Trade-off between accessibility and accuracy Step-by-step, pause and review approach seems appropriate Transparency is essential Standardization of practices between international organizations would help Steven Vale - UNECE Statistical Division Slide 12 Open questions 1. 2.

3. 4. Are other organizations interested in defining a common policy on the use of imputation, in response to the ECOSOC Resolution? Could we go further and consider harmonization of methods and tools? How should this be done? Is a specific forum needed, or can this be dealt with in combination with work on data quality? Have other organizations modified their policies on imputation in the light of the ECOSOC Resolution, and if so, how? Steven Vale - UNECE Statistical Division Slide 13

Recently Viewed Presentations

  • EL Strategic Plan Status and Update

    EL Strategic Plan Status and Update

    Taffy Carlisle - Education Specialist, Equity & English Learners. Oregon Department of Education. Office of the Deputy Superintendent . ... Indian Ed discussions on culturally appropriate communication. Dual Language Grant commitment to parent understanding and communication .
  • Chapter 1: Matter and Measurement - athena.uwindsor.ca

    Chapter 1: Matter and Measurement - athena.uwindsor.ca

    General Chemistry Principles and Modern Applications Petrucci • Harwood • Herring 8th Edition Chapter 5: Introduction to Reactions in Aqueous Solutions
  • The Man Who Named the Clouds - PC\|MAC

    The Man Who Named the Clouds - PC\|MAC

    Used in the text… Pg. 181, Paragraph 1. Before they even hit the ground, smokejumpers are hard at work tracking the fire, finding the right place to jump, and concentrating on landing safely.
  • Conversations for a One Planet Region - Home - Public Health ...

    Conversations for a One Planet Region - Home - Public Health ...

    Source: WWF Living Planet Report 2016 (p 75) / Global Footprint Network, 2016. In 2012, the biocapacity equivalent of 1.6 Earths was needed to provide the natural resources and services humanity consumed in that year . Source: WWF Living Planet...
  • Tax Practice Chapter 6 pp.157-203 2018 National Income

    Tax Practice Chapter 6 pp.157-203 2018 National Income

    Federal Tax Levy p. 174 Requirements for IRS to Levy Tax assessed & IRS sent Notice & Demand for Payment to TP TP neglected/refused to pay IRS sent Final Notice of Intent to Levy and Notice of Your Right to...
  • Phononen in Fe65Ni35 Temperatur- und Druckabhängigkeit

    Phononen in Fe65Ni35 Temperatur- und Druckabhängigkeit

    • These "anomalous" properties are reflected in particular by the Debye temperatures QD,HT and QD,LT and Grüneisen parameters gHT and gLT, derived from the high-energy and low-energy part of the DOS; they disappear with the suppression of the Fe moment...
  • GCSE Art and Design First teaching in 2016.

    GCSE Art and Design First teaching in 2016.

    to help you deliver AQA Art and Design qualifications. Subject expertise: courses for all teachers, from newly-qualified teachers who are just getting started to experienced teachers looking for fresh inspiration.
  • CS 475: Uncertainty and Multi-Agent Systems Prof. Bart

    CS 475: Uncertainty and Multi-Agent Systems Prof. Bart

    CS 475: Uncertainty and Multi-Agent Systems Prof. Bart Selman [email protected] Introduction Overview of this Lecture Motivation behind new course Course administration Role of uncertainty and multi-agent systems in AI Motivation Course Administration Grading (tentative) Textbook Emergence of Uncertainty in AI...